Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1147 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.5160. Min Act: -0.0000

Data Index: 872400 (The Pile)

Max Activating Token Index: 121

Text #1

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3191. Min Act: -0.0000

Data Index: 1010322 (The Pile)

Max Activating Token Index: 882

Text #2

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.2597. Min Act: -0.0000

Data Index: 1999950 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.0625. Min Act: -0.0000

Data Index: 445469 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.2884. Min Act: -0.0000

Data Index: 12969 (The Pile)

Max Activating Token Index: 437

Text #5

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.1274. Min Act: -0.0000

Data Index: 1841810 (The Pile)

Max Activating Token Index: 550

Text #6

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.0231. Min Act: -0.0000

Data Index: 965174 (The Pile)

Max Activating Token Index: 827

Text #7

Max Range: 3.5160. Min Range: -3.5160

Max Act: 2.9939. Min Act: -0.0000

Data Index: 644962 (The Pile)

Max Activating Token Index: 833

Text #8

Max Range: 3.5160. Min Range: -3.5160

Max Act: 2.8671. Min Act: -0.0000

Data Index: 996204 (The Pile)

Max Activating Token Index: 95

Text #9

Max Range: 3.5160. Min Range: -3.5160

Max Act: 2.7921. Min Act: -0.0000

Data Index: 1348347 (The Pile)

Max Activating Token Index: 284

Text #10

Max Range: 3.5160. Min Range: -3.5160

Max Act: 2.7871. Min Act: -0.0000

Data Index: 1528243 (The Pile)

Max Activating Token Index: 66

Text #11

Max Range: 3.5160. Min Range: -3.5160

Max Act: 2.7828. Min Act: -0.0000

Data Index: 242280 (The Pile)

Max Activating Token Index: 172

Text #12

Max Range: 3.5160. Min Range: -3.5160

Max Act: 2.9035. Min Act: -0.0000

Data Index: 1841439 (The Pile)

Max Activating Token Index: 760

Text #13

Max Range: 3.5160. Min Range: -3.5160

Max Act: 2.6239. Min Act: -0.0000

Data Index: 736588 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 3.5160. Min Range: -3.5160

Max Act: 2.7176. Min Act: -0.0000

Data Index: 1323946 (The Pile)

Max Activating Token Index: 578

Text #15

Max Range: 3.5160. Min Range: -3.5160

Max Act: 2.5827. Min Act: -0.0000

Data Index: 1990324 (The Pile)

Max Activating Token Index: 469

Text #16

Max Range: 3.5160. Min Range: -3.5160

Max Act: 2.5526. Min Act: -0.0000

Data Index: 1313178 (The Pile)

Max Activating Token Index: 87

Text #17

Max Range: 3.5160. Min Range: -3.5160

Max Act: 2.6558. Min Act: -0.0000

Data Index: 891078 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 3.5160. Min Range: -3.5160

Max Act: 2.6375. Min Act: -0.0000

Data Index: 1701959 (The Pile)

Max Activating Token Index: 419

Text #19

Max Range: 3.5160. Min Range: -3.5160

Max Act: 2.6086. Min Act: -0.0000

Data Index: 187728 (The Pile)

Max Activating Token Index: 753